Beyond Polarity: Multi-Dimensional LLM Sentiment Signals for WTI Crude Oil Futures Return Prediction

2026-03-11

AI Summary

This study addresses the limitations of traditional polarity-based sentiment analysis in capturing the multidimensional information embedded in energy news that exhibits predictive power for WTI crude oil futures prices. Moving beyond a unidimensional polarity framework, the authors propose a comprehensive sentiment indicator system encompassing five dimensions: relevance, polarity, intensity, uncertainty, and forward-lookingness. They integrate signals extracted via GPT-4o, Llama 3.2-3B, FinBERT, and AlphaVantage, and employ a classification-based forecasting framework augmented with SHAP interpretability analysis to predict weekly returns. Experimental results demonstrate that the ensemble model combining GPT-4o and FinBERT achieves superior predictive performance, significantly improving accuracy and confirming the effectiveness and practical value of multidimensional large language model–derived sentiment signals for risk monitoring in energy markets.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Forecasting crude oil prices remains challenging because market-relevant information is embedded in large volumes of unstructured news and is not fully captured by traditional polarity-based sentiment measures. This paper examines whether multi-dimensional sentiment signals extracted by large language models improve the prediction of weekly WTI crude oil futures returns. Using energy-sector news articles from 2020 to 2025, we construct five sentiment dimensions covering relevance, polarity, intensity, uncertainty, and forwardness based on GPT-4o, Llama 3.2-3b, and two benchmark models, FinBERT and AlphaVantage. We aggregate article-level signals to the weekly level and evaluate their predictive performance in a classification framework. The best results are achieved by combining GPT-4o and FinBERT, suggesting that LLM-based and conventional financial sentiment models provide complementary predictive information. SHAP analysis further shows that intensity- and uncertainty-related features are among the most important predictors, indicating that the predictive value of news sentiment extends beyond simple polarity. Overall, the results suggest that multi-dimensional LLM-based sentiment measures can improve commodity return forecasting and support energy-market risk monitoring.

Problem

• sentiment analysis
• crude oil futures
• return prediction
• large language models
• financial news

Innovation

• multi-dimensional sentiment
• large language models
• commodity forecasting
• WTI crude oil futures
• sentiment intensity